Key Capabilities
- 1M token context window — Handles massive documents and conversations, up to 65,000 output tokens
- Thinking levels — Control reasoning depth via
minimal,low,medium(default), andhigh - Thinking persistence — Model automatically retains intermediate reasoning across multi-turn conversations
- Agentic execution — Optimized for multi-agent deployments, problem solving, and large-scale agentic loops
- Coding — Excels at iterative coding cycles, rapid exploration, and prototyping
- Production-ready — Stable model, suitable for large-scale production use
Quick Example
Parameters
API Reference
View the interactive API Playground for Gemini 3.5 Flash.

